Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department.

Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department

Machine Translation 美国关岛国际机场及其办公室均接获一名自称沙地阿拉伯富商拉登等发出的电子邮件，威胁将会向机场等公众地方发动生化袭击後，关岛经保持高度戒备。 The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport. The classic acid test for natural language processing. Requires capabilities in both interpretation and generation. About $10 billion spent annually on human translation.

Knowledge Acquisition Strategy Knowledge Representation Strategy All manual Deep/ Complex Shallow/ Simple Fully automated Learn from un- annotated data Phrase tables Word-based only Learn from annotated data Example-based MT Original statistical MT Typical transfer system Classic interlingual system Original direct approach Syntactic Constituent Structure Interlingua New Research Goes Here! Semantic analysis Hand-built by non-experts Hand-built by experts Electronic dictionaries MT Strategies (1954-2004) Slide courtesy of Laurie Gerber

Data-Driven Machine Translation Hmm, every time he sees “banco”, he either types “bank” or “bench” … but if he sees “banco de…”, he always types “bank”, never “bench”… Man, this is so boring. Translated documents

Recent Progress in Statistical MT insistent Wednesday may recurred her trips to Libya tomorrow for flying Cairo 6-4 ( AFP ) - an official announced today in the Egyptian lines company for flying Tuesday is a company " insistent for flying " may resumed a consideration of a day Wednesday tomorrow her trips to Libya of Security Council decision trace international the imposed ban comment. And said the official " the institution sent a speech to Ministry of Foreign Affairs of lifting on Libya air, a situation her receiving replying are so a trip will pull to Libya a morning Wednesday ". Egyptair Has Tomorrow to Resume Its Flights to Libya Cairo 4-6 (AFP) - said an official at the Egyptian Aviation Company today that the company egyptair may resume as of tomorrow, Wednesday its flights to Libya after the International Security Council resolution to the suspension of the embargo imposed on Libya. " The official said that the company had sent a letter to the Ministry of Foreign Affairs, information on the lifting of the air embargo on Libya, where it had received a response, the first take off a trip to Libya on Wednesday morning ". 2002 2003 slide from C. Wayne, DARPA

Centauri/Arcturan [Knight, 1997] Your assignment, translate this to Arcturan: farok crrrok hihok yorok clok kantok ok-yurp

Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat. Your assignment, translate this to Arcturan: farok crrrok hihok yorok clok kantok ok-yurp

Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat.

Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat. Your assignment, translate this to Arcturan: farok crrrok hihok yorok clok kantok ok-yurp ???

Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat. Your assignment, translate this to Arcturan: farok crrrok hihok yorok clok kantok ok-yurp process of elimination

Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat. Your assignment, translate this to Arcturan: farok crrrok hihok yorok clok kantok ok-yurp cognate?

Your assignment, put these words in order: { jjat, arrat, mat, bat, oloat, at-yurp } Centauri/Arcturan [Knight, 1997] 1a. ok-voon ororok sprok. 1b. at-voon bichat dat. 7a. lalok farok ororok lalok sprok izok enemok. 7b. wat jjat bichat wat dat vat eneat. 2a. ok-drubel ok-voon anok plok sprok. 2b. at-drubel at-voon pippat rrat dat. 8a. lalok brok anok plok nok. 8b. iat lat pippat rrat nnat. 3a. erok sprok izok hihok ghirok. 3b. totat dat arrat vat hilat. 9a. wiwok nok izok kantok ok-yurp. 9b. totat nnat quat oloat at-yurp. 4a. ok-voon anok drok brok jok. 4b. at-voon krat pippat sat lat. 10a. lalok mok nok yorok ghirok clok. 10b. wat nnat gat mat bat hilat. 5a. wiwok farok izok stok. 5b. totat jjat quat cat. 11a. lalok nok crrrok hihok yorok zanzanok. 11b. wat nnat arrat mat zanzanat. 6a. lalok sprok izok jok stok. 6b. wat dat krat quat cat. 12a. lalok rarok nok izok hihok mok. 12b. wat nnat forat arrat vat gat. zero fertility

Clients do not sell pharmaceuticals in Europe => Clientes no venden medicinas en Europa It’s Really Spanish/English 1a. Garcia and associates. 1b. Garcia y asociados. 7a. the clients and the associates are enemies. 7b. los clients y los asociados son enemigos. 2a. Carlos Garcia has three associates. 2b. Carlos Garcia tiene tres asociados. 8a. the company has three groups. 8b. la empresa tiene tres grupos. 3a. his associates are not strong. 3b. sus asociados no son fuertes. 9a. its groups are in Europe. 9b. sus grupos estan en Europa. 4a. Garcia has a company also. 4b. Garcia tambien tiene una empresa. 10a. the modern groups sell strong pharmaceuticals. 10b. los grupos modernos venden medicinas fuertes. 5a. its clients are angry. 5b. sus clientes estan enfadados. 11a. the groups do not sell zenzanine. 11b. los grupos no venden zanzanina. 6a. the associates are also angry. 6b. los asociados tambien estan enfadados. 12a. the small groups are not modern. 12b. los grupos pequenos no son modernos.

Data for Statistical MT and data preparation

Ready-to-Use Online Bilingual Data (Data stripped of formatting, in sentence-pair format, available from the Linguistic Data Consortium at UPenn). Millions of words (English side)

Ready-to-Use Online Bilingual Data (Data stripped of formatting, in sentence-pair format, available from the Linguistic Data Consortium at UPenn). Millions of words (English side) + 1m-20m words for many language pairs

Ready-to-Use Online Bilingual Data Millions of words (English side)  One Billion? ???

From No Data to Sentence Pairs Easy way: Linguistic Data Consortium (LDC) Really hard way: pay $$$ –Suppose one billion words of parallel data were sufficient –At 20 cents/word, that’s $200 million Pretty hard way: Find it, and then earn it! –De-formatting –Remove strange characters –Character code conversion –Document alignment –Sentence alignment –Tokenization (also called Segmentation)

Sentence Alignment The old man is happy. He has fished many times. His wife talks to him. The fish are jumping. The sharks await. El viejo está feliz porque ha pescado muchos veces. Su mujer habla con é l. Los tiburones esperan.

Sentence Alignment 1.The old man is happy. 2.He has fished many times. 3.His wife talks to him. 4.The fish are jumping. 5.The sharks await. 1.El viejo está feliz porque ha pescado muchos veces. 2.Su mujer habla con él. 3.Los tiburones esperan.

Sentence Alignment 1.The old man is happy. He has fished many times. 2.His wife talks to him. 3.The sharks await. 1.El viejo está feliz porque ha pescado muchos veces. 2.Su mujer habla con él. 3.Los tiburones esperan. Note that unaligned sentences are thrown out, and sentences are merged in n-to-m alignments (n, m > 0).

Tokenization (or Segmentation) English –Input (some byte stream): "There," said Bob. –Output (7 “tokens” or “words”): " There, " said Bob. Chinese –Input (byte stream): –Output: 美国关岛国际机场及其办公室均接获一名自称沙地阿拉伯富商拉登等发出的电子邮件。

Lower-Casing English –Input (7 words): " There, " said Bob. –Output (7 words): " there, " said bob. The the “The “the the Smaller vocabulary size. More robust counting and learning. Idea of tokenizing and lower-casing:

It Is Possible to Draw Learning Curves: How Much Data Do We Need? Amount of bilingual training data Quality of automatically trained machine translation system

MT Evaluation

Manual: –SSER (subjective sentence error rate) –Correct/Incorrect –Error categorization Testing in an application that uses MT as one sub-component –Question answering from foreign language documents Automatic: –WER (word error rate) –BLEU (Bilingual Evaluation Understudy)

Reference (human) translation: The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport. Machine translation: The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail, which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack, [?] highly alerts after the maintenance. BLEU Evaluation Metric (Papineni et al, ACL-2002) N-gram precision (score is between 0 & 1) –What percentage of machine n-grams can be found in the reference translation? –An n-gram is an sequence of n words –Not allowed to use same portion of reference translation twice (can’t cheat by typing out “the the the the the”) Brevity penalty –Can’t just type out single word “the” (precision 1.0!) *** Amazingly hard to “game” the system (i.e., find a way to change machine output so that BLEU goes up, but quality doesn’t)

Reference (human) translation: The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport. Machine translation: The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail, which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack, [?] highly alerts after the maintenance. BLEU Evaluation Metric (Papineni et al, ACL-2002) BLEU4 formula (counts n-grams up to length 4) exp (1.0 * log p1 + 0.5 * log p2 + 0.25 * log p3 + 0.125 * log p4 – max(words-in-reference / words-in-machine – 1, 0) p1 = 1-gram precision P2 = 2-gram precision P3 = 3-gram precision P4 = 4-gram precision

Reference translation 1: The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport. Reference translation 3: The US International Airport of Guam and its office has received an email from a self-claimed Arabian millionaire named Laden, which threatens to launch a biochemical attack on such public places as airport. Guam authority has been on alert. Reference translation 4: US Guam International Airport and its office received an email from Mr. Bin Laden and other rich businessman from Saudi Arabia. They said there would be biochemistry air raid to Guam Airport and other public places. Guam needs to be in high precaution about this matter. Reference translation 2: Guam International Airport and its offices are maintaining a high state of alert after receiving an e-mail that was from a person claiming to be the wealthy Saudi Arabian businessman Bin Laden and that threatened to launch a biological and chemical attack on the airport and other public places. Machine translation: The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail, which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack, [?] highly alerts after the maintenance. Multiple Reference Translations Reference translation 1: The U.S. island of Guam is maintaining a high state of alert after the Guam airport and its offices both received an e-mail from someone calling himself the Saudi Arabian Osama bin Laden and threatening a biological/chemical attack against public places such as the airport. Reference translation 3: The US International Airport of Guam and its office has received an email from a self-claimed Arabian millionaire named Laden, which threatens to launch a biochemical attack on such public places as airport. Guam authority has been on alert. Reference translation 4: US Guam International Airport and its office received an email from Mr. Bin Laden and other rich businessman from Saudi Arabia. They said there would be biochemistry air raid to Guam Airport and other public places. Guam needs to be in high precaution about this matter. Reference translation 2: Guam International Airport and its offices are maintaining a high state of alert after receiving an e-mail that was from a person claiming to be the wealthy Saudi Arabian businessman Bin Laden and that threatened to launch a biological and chemical attack on the airport and other public places. Machine translation: The American [?] international airport and its the office all receives one calls self the sand Arab rich business [?] and so on electronic mail, which sends out ; The threat will be able after public place and so on the airport to start the biochemistry attack, [?] highly alerts after the maintenance.

BLEU Tends to Predict Human Judgments slide from G. Doddington (NIST) (variant of BLEU)

BLEU in Action 枪手被警方击毙。 (Foreign Original) the gunman was shot to death by the police. (Reference Translation) the gunman was police kill. #1 wounded police jaya of #2 the gunman was shot dead by the police. #3 the gunman arrested by police kill. #4 the gunmen were killed. #5 the gunman was shot to death by the police. #6 gunmen were killed by police ?SUB>0 ?SUB>0 #7 al by the police. #8 the ringer is killed by the police. #9 police killed the gunman. #10

BLEU in Action 枪手被警方击毙。 (Foreign Original) the gunman was shot to death by the police. (Reference Translation) the gunman was police kill. #1 wounded police jaya of #2 the gunman was shot dead by the police. #3 the gunman arrested by police kill. #4 the gunmen were killed. #5 the gunman was shot to death by the police. #6 gunmen were killed by police ?SUB>0 ?SUB>0 #7 al by the police. #8 the ringer is killed by the police. #9 police killed the gunman. #10 green = 4-gram match (good!) red = word not matched (bad!)

Sample Learning Curves Swedish/English French/English German/English Finnish/English # of sentence pairs used in training BLEU score Experiments by Philipp Koehn

Word-Based Statistical MT

Statistical MT Systems Spanish Broken English Spanish/English Bilingual Text English Text Statistical Analysis Que hambre tengo yo What hunger have I, Hungry I am so, I am so hungry, Have I that hunger … I am so hungry

Statistical MT Systems Spanish Broken English Spanish/English Bilingual Text English Text Statistical Analysis Que hambre tengo yoI am so hungry Translation Model P(s|e) Language Model P(e) Decoding algorithm argmax P(e) * P(s|e) e

Bayes Rule Spanish Broken English Que hambre tengo yoI am so hungry Translation Model P(s|e) Language Model P(e) Decoding algorithm argmax P(e) * P(s|e) e Given a source sentence s, the decoder should consider many possible translations … and return the target string e that maximizes P(e | s) By Bayes Rule, we can also write this as: P(e) x P(s | e) / P(s) and maximize that instead. P(s) never changes while we compare different e’s, so we can equivalently maximize this: P(e) x P(s | e)

Three Problems for Statistical MT Language model –Given an English string e, assigns P(e) by formula –good English string -> high P(e) –random word sequence -> low P(e) Translation model –Given a pair of strings, assigns P(f | e) by formula – look like translations -> high P(f | e) – don’t look like translations -> low P(f | e) Decoding algorithm –Given a language model, a translation model, and a new sentence f … find translation e maximizing P(e) * P(f | e)

The Classic Language Model Word N-Grams Goal of the language model -- choose among: He is on the soccer field He is in the soccer field Is table the on cup the The cup is on the table Rice shrine American shrine Rice company American company

Translation Model? Mary did not slap the green witch Maria no d ió una botefada a la bruja verde Source-language morphological analysis Source parse tree Semantic representation Generate target structure Generative approach:

Translation Model? Mary did not slap the green witch Maria no d ió una botefada a la bruja verde Source-language morphological analysis Source parse tree Semantic representation Generate target structure Generative story: What are all the possible moves and their associated probability tables?

The Classic Translation Model Word Substitution/Permutation [IBM Model 3, Brown et al., 1993] Mary did not slap the green witch Mary not slap slap slap the green witch n(3|slap) Maria no d ió una botefada a la bruja verde d(j|i) Mary not slap slap slap NULL the green witch P-Null Maria no d ió una botefada a la verde bruja t(la|the) Generative approach: Probabilities can be learned from raw bilingual text.

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … All word alignments equally likely All P(french-word | english-word) equally likely

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … “la” and “the” observed to co-occur frequently, so P(la | the) is increased.

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … “house” co-occurs with both “la” and “maison”, but P(maison | house) can be raised without limit, to 1.0, while P(la | house) is limited because of “the” (pigeonhole principle)

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … settling down after another iteration

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … Inherent hidden structure revealed by EM training! For details, see: “A Statistical MT Tutorial Workbook” (Knight, 1999). “The Mathematics of Statistical Machine Translation” (Brown et al, 1993) Software: GIZA++

Statistical Machine Translation … la maison … la maison bleue … la fleur … … the house … the blue house … the flower … P(juste | fair) = 0.411 P(juste | correct) = 0.027 P(juste | right) = 0.020 … new French sentence Possible English translations, to be rescored by language model

Decoding for “Classic” Models Of all conceivable English word strings, find the one maximizing P(e) x P(f | e) Decoding is an NP-complete challenge –(Knight, 1999) Several search strategies are available Each potential English output is called a hypothesis.

Greedy decoding (Germann et al, ACL-2001)

Dynamic Programming Beam Search 1 st target word 2 nd target word 3 rd target word 4 th target word start end Each partial translation hypothesis contains: - Last English word chosen + source words covered by it - Next-to-last English word chosen - Entire coverage vector (so far) of source sentence - Language model and translation model scores (so far) all source words covered [Jelinek, 1969; Brown et al, 1996 US Patent; (Och, Ueffing, and Ney, 2001]

Dynamic Programming Beam Search 1 st target word 2 nd target word 3 rd target word 4 th target word start end Each partial translation hypothesis contains: - Last English word chosen + source words covered by it - Next-to-last English word chosen - Entire coverage vector (so far) of source sentence - Language model and translation model scores (so far) all source words covered [Jelinek, 1969; Brown et al, 1996 US Patent; (Och, Ueffing, and Ney, 2001] best predecessor link

The Classic Results la politique de la haine. (Foreign Original) politics of hate. (Reference Translation) the policy of the hatred. (IBM4+N-grams+Stack) nous avons signé le protocole. (Foreign Original) we did sign the memorandum of agreement. (Reference Translation) we have signed the protocol. (IBM4+N-grams+Stack) où était le plan solide ? (Foreign Original) but where was the solid plan ? (Reference Translation) where was the economic base ? (IBM4+N-grams+Stack) the Ministry of Foreign Trade and Economic Cooperation, including foreign direct investment 40.007 billion US dollars today provide data include that year to November china actually using foreign 46.959 billion US dollars and

Flaws of Word-Based MT Multiple English words for one French word –IBM models can do one-to-many (fertility) but not many-to-one Phrasal Translation –“real estate”, “note that”, “interest in” Syntactic Transformations –Verb at the beginning in Arabic –Translation model penalizes any proposed re- ordering –Language model not strong enough to force the verb to move to the right place

Phrase-Based Statistical MT

Foreign input segmented in to phrases –“phrase” is any sequence of words Each phrase is probabilistically translated into English –P(to the conference | zur Konferenz) –P(into the meeting | zur Konferenz) Phrases are probabilistically re-ordered See [Koehn et al, 2003] for an intro. This is state-of-the-art! Morgenfliegeichnach Kanadazur Konferenz TomorrowIwill flyto the conferenceIn Canada

Advantages of Phrase-Based Many-to-many mappings can handle non- compositional phrases Local context is very useful for disambiguating –“Interest rate”  … –“Interest in”  … The more data, the longer the learned phrases –Sometimes whole sentences

How to Learn the Phrase Translation Table? One method: “alignment templates” (Och et al, 1999) Start with word alignment, build phrases from that. Mary did not slap the green witch Maria no dió una bofetada a la bruja verde This word-to-word alignment is a by-product of training a translation model like IBM-Model-3. This is the best (or “Viterbi”) alignment.

IBM Models are 1-to-Many Run IBM-style aligner both directions, then merge: E  F best alignment Union or Intersection MERGE F  E best alignment

How to Learn the Phrase Translation Table? Collect all phrase pairs that are consistent with the word alignment Mary did not slap the green witch Maria no dió una bofetada a la bruja verde one example phrase pair

Consistent with Word Alignment Phrase alignment must contain all alignment points for all the words in both phrases! x x Mary did not slap Maria no dió Mary did not slap Maria no dió Mary did not slap Maria no dió consistentinconsistent

Mary did not slap the green witch Maria no dió una bofetada a la bruja verde Word Alignment Induced Phrases (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green)

Mary did not slap the green witch Maria no dió una bofetada a la bruja verde Word Alignment Induced Phrases (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the)

Mary did not slap the green witch Maria no dió una bofetada a la bruja verde Word Alignment Induced Phrases (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the) (Maria no, Mary did not) (no dió una bofetada, did not slap), (dió una bofetada a la, slap the) (bruja verde, green witch)

Mary did not slap the green witch Maria no dió una bofetada a la bruja verde Word Alignment Induced Phrases (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the) (Maria no, Mary did not) (no dió una bofetada, did not slap), (dió una bofetada a la, slap the) (bruja verde, green witch) (Maria no dió una bofetada, Mary did not slap) (a la bruja verde, the green witch) …

Mary did not slap the green witch Maria no dió una bofetada a la bruja verde Word Alignment Induced Phrases (Maria, Mary) (no, did not) (slap, dió una bofetada) (la, the) (bruja, witch) (verde, green) (a la, the) (dió una bofetada a, slap the) (Maria no, Mary did not) (no dió una bofetada, did not slap), (dió una bofetada a la, slap the) (bruja verde, green witch) (Maria no dió una bofetada, Mary did not slap) (a la bruja verde, the green witch) … (Maria no dió una bofetada a la bruja verde, Mary did not slap the green witch)

Phrase Pair Probabilities A certain phrase pair (f-f-f, e-e-e) may appear many times across the bilingual corpus. –We hope so! So, now we have a vast list of phrase pairs and their frequencies – how to assign probabilities?

Phrase Pair Probabilities Basic idea: –No EM training –Just relative frequency: P(f-f-f | e-e-e) = count(f-f-f, e-e-e) / count(e-e-e) Important refinements: –Smooth using word probs P(f | e) for individual words connected in the word alignment Some low count phrase pairs now have high probability, others have low probability –Discount for ambiguity If phrase e-e-e can map to 5 different French phrases, due to the ambiguity of unaligned words, each pair gets a 1/5 count –Count BAD events too If phrase e-e-e doesn’t map onto any contiguous French phrase, increment event count(BAD, e-e-e)

Advanced Training Methods

Basic Model, Revisited argmax P(e | f) = e argmax P(e) x P(f | e) / P(f) = e argmax P(e) x P(f | e) e

Basic Model, Revisited argmax P(e | f) = e argmax P(e) x P(f | e) / P(f) = e argmax P(e) 2.4 x P(f | e) … works better! e

Basic Model, Revisited argmax P(e | f) = e argmax P(e) x P(f | e) / P(f) e argmax P(e) 2.4 x P(f | e) x length(e) 1.1 e Rewards longer hypotheses, since these are unfairly punished by P(e)

Basic Model, Revisited argmax P(e) 2.4 x P(f | e) x length(e) 1.1 x KS 3.7 … e Lots of knowledge sources vote on any given hypothesis. “Knowledge source” = “feature function” = “score component”. Feature function simply scores a hypothesis with a real value. (May be binary, as in “e has a verb”). Problem: How to set the exponent weights?

Maximum BLEU Training (Och, 2003) Translation System (Automatic, Trainable) Translation Quality Evaluator (Automatic) Farsi English MT Output English Reference Translations (sample “right answers”) BLEU score Language Model #1 Translation Model Language Model #2 Length Model Other Features Learning Algorithm for Directly Reducing Translation Error Yields big improvements in quality.

Syntax and Semantics in Statistical MT

MT Pyramid SOURCETARGET words syntax semantics interlingua phrases

Why Syntax? Need much more grammatical output Need accurate control over re-ordering Need accurate insertion of function words Word translations need to depend on grammatically-related words

. Reorder VB PRPVB2 VB1 TOVB MN TO he adores listening music to Insert desu VB PRPVB2VB1 TOVB MNTO he ha music to ga adores listeningno Translate Kare ha ongaku wo kiku no ga daisuki desu Take Leaves desu VB PRPVB2VB1 TOVB MNTO kare ha ongaku wo ga daisuki kikuno VB PRPVB1 headores listening VB2 VBTO MNTO musicto Parse Tree(E) Sentence(J) Yamada/Knight 01: Modeling and Training

Japanese/English Reorder Table For French/English, useful parameters like P(N ADJ | ADJ N).

Decoded Tree he briefed reporters statement major contents he briefed reporters on main contents of the stmt PRP NPB S PRN NPB S PRN NPB NP VBDNNSNNJJNNS NPB VP NPB S PRN PRPVBDNNSINJJNNSINDTNN NPB PP NP-A PP VP S Decoding with Trigram LMDecoding with Charniak Tree-Based LM

Casting Syntax MT Models As Tree Transducer Automata [Graehl & Knight 04] q S NP1VP VBNP2 S NP1VP NP2 q S PROVP VBNPthere are two men CDNN S PRNP hay dos hombres CD NN NP NP1PP of PNP2 NP NP2 P NP1 q S WH-NPSINV/NP MDS/NPWho did NPVP/NP VB see S Ska SNP S VB PROP dareo NPP ga * Non-local Re-Ordering (English/Arabic)Non-constituent Phrasal Translation (English/Spanish) Lexicalized Re-Ordering (English/Chinese)Long-distance Re-Ordering (English/Japanese)

Summary Phrase-based models are state-of-the-art –Word alignments –Phrase pair extraction & probabilities –N-gram language models –Beam search decoding –Feature functions & learning weights But the output is not English –Fluency must be improved –Better translation of person names, organizations, locations –More automatic acquisition of parallel data, exploitation of monolingual data across a variety of domains/languages –Need good accuracy across a variety of domains/languages

Available Resources Bilingual corpora –100m+ words of Chinese/English and Arabic/English, LDC (www.ldc.upenn.edu) –Lots of French/English, Spanish/French/English, LDC –European Parliament (sentence-aligned), 11 languages, Philipp Koehn, ISI (www.isi.edu/~koehn/publications/europarl) –20m words (sentence-aligned) of English/French, Ulrich Germann, ISI (www.isi.edu/natural-language/download/hansard/)www.isi.edu/natural-language/download/hansard/ Sentence alignment –Dan Melamed, NYU (www.cs.nyu.edu/~melamed/GMA/docs/README.htm) –Xiaoyi Ma, LDC (Champollion) Word alignment –GIZA, JHU Workshop ’99 (www.clsp.jhu.edu/ws99/projects/mt/) –GIZA++, RWTH Aachen (www-i6.Informatik.RWTH-Aachen.de/web/Software/GIZA++.html) –Manually word-aligned test corpus (500 French/English sentence pairs), RWTH Aachen –Shared task, NAACL-HLT’03 workshop Decoding –ISI ReWrite Model 4 decoder (www.isi.edu/licensed-sw/rewrite-decoder/)www.isi.edu/licensed-sw/rewrite-decoder/ –ISI Pharoah phrase-based decoder Statistical MT Tutorial Workbook, ISI (www.isi.edu/~knight/) Annual common-data evaluation, NIST (www.nist.gov/speech/tests/mt/index.htm)

Some Papers Referenced on Slides ACL –[Och, Tillmann, & Ney, 1999] –[Och & Ney, 2000] –[Germann et al, 2001] –[Yamada & Knight, 2001, 2002] –[Papineni et al, 2002] –[Alshawi et al, 1998] –[Collins, 1997] –[Koehn & Knight, 2003] –[Al-Onaizan & Knight, 2002] –[Och & Ney, 2002] –[Och, 2003] –[Koehn et al, 2003] EMNLP –[Marcu & Wong, 2002] –[Fox, 2002] –[Munteanu & Marcu, 2002] AI Magazine –[Knight, 1997] www.isi.edu/~knight –[MT Tutorial Workbook] AMTA –[Soricut et al, 2002] –[Al-Onaizan & Knight, 1998] EACL –[Cmejrek et al, 2003] Computational Linguistics –[Brown et al, 1993] –[Knight, 1999] –[Wu, 1997] AAAI –[Koehn & Knight, 2000] IWNLG –[Habash, 2002] MT Summit –[Charniak, Knight, Yamada, 2003] NAACL –[Koehn, Marcu, Och, 2003] –[Germann, 2003] –[Graehl & Knight, 2004] –[Galley, Hopkins, Knight, Marcu, 2004]

Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department.

Similar presentations

Presentation on theme: "Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department."— Presentation transcript:

Similar presentations

About project

Feedback

Log in

Auth with social network:

Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department.

Similar presentations

Presentation on theme: "Statistical Machine Translation Kevin Knight USC/Information Sciences Institute USC/Computer Science Department."— Presentation transcript:

Similar presentations

About project

Feedback